PROGRAMMING METHOD OF AN ACTIVATION FUNCTION AND AN ACTIVATION FUNCTION PROGRAMMING UNIT

    公开(公告)号:US20250148272A1

    公开(公告)日:2025-05-08

    申请号:US19007909

    申请日:2025-01-02

    Abstract: An activation function conversion program unit and method may be configured to approximate a target activation function to a programmed activation function through machine-learning of an artificial neural network. The method may include setting up a target activation function; approximating the target activation function to a programmed activation function by machine-learning an artificial neural network; and converting the programmed activation function into a slope and offset and storing it in a lookup table. Accordingly, the computation speed and power consumption of the programmed activation function execution unit of an NPU may be optimized.

    METHOD FOR GENERATING PROGRAMMABLE ACTIVATION FUNCTION AND APPARATUS USING THE SAME

    公开(公告)号:US20230169314A1

    公开(公告)日:2023-06-01

    申请号:US17750568

    申请日:2022-05-23

    CPC classification number: G06N3/0481

    Abstract: A method for programming an activation function is provided. The method includes generating segment data for segmenting the activation function; segmenting the activation function into a plurality of segments using the segment data; and approximating at least one segment of the plurality of segments as a programmable segment. An apparatus for performing the method may include a programmable activation function generator configured to generate segment data for segmenting an activation function; segment the activation function into a plurality of segments using the generated segment data; and approximate at least one segment of the plurality of segments as a programmable segment. By using segment data, various non-linear activation functions, particularly newly proposed or known activation functions with some modifications, can be programmed to be processable in hardware.

Patent Agency Ranking